Intelligent automatic assembling method and system for electric vehicle components

Abstract

The invention relates to the technical field of automatic assembly, in particular to an intelligent automatic assembly method and system for an electric vehicle component, and the method comprises the steps: carrying out the modular design of the electric vehicle component, and developing a standardized interface for the electric vehicle component; analyzing electric vehicle production requirements, and making an electric vehicle assembly plan; distributing the assembly plan to each workstation device; a neural network structure is selected to construct an electric vehicle assembly monitoring model, the electric vehicle assembly process is monitored through the electric vehicle assembly monitoring model, and an electric vehicle assembly monitoring result is obtained; and the assembly plan is adjusted according to the electric vehicle assembly monitoring result. Through the modular design and introduction of a standardized interface, and by adopting an advanced neural network technology and an intelligent monitoring system, the electric vehicle assembling efficiency can be improved, the assembling strategy can be adjusted in time, the production flexibility and the optimal configuration of resources can be enhanced, and flexible manufacturing of multi-vehicle-type and multi-configuration electric vehicles can be achieved.

Description

Technical Field

[0001] The present invention relates to the field of automated assembly technology, and in particular to an intelligent automated assembly method and system for electric vehicle components. Background Art

[0002] As the world's awareness of green energy and environmental protection continues to increase, the electric vehicle market is developing rapidly. Due to its environmental protection and energy-saving advantages, electric vehicles are gradually becoming an important means of transportation to replace traditional fuel vehicles. As the mainstream direction of the future automotive industry, the production and assembly efficiency of electric vehicles is directly related to its market competitiveness.

[0003] At present, most electric vehicle assembly lines still rely on traditional assembly line production methods. Although some processes have been automated, the entire assembly process still requires a lot of manpower. At the same time, with the increasing complexity of electric vehicle design, the traditional assembly line has a low degree of automation, and the production monitoring and feedback mechanism is imperfect. It is impossible to achieve flexible manufacturing of electric vehicles with multiple models and configurations, and it is difficult to meet personalized customization needs, resulting in insufficient production flexibility. Therefore, an intelligent automated assembly method for electric vehicle components has become one of the current research directions. Summary of the invention

[0004] The present invention provides an intelligent automatic assembly method and system for electric vehicle components, which can effectively solve the problems in the background technology.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is: An intelligent and automated assembly method for electric vehicle components, the method comprising: Modularize the design of electric vehicle components and develop standardized interfaces for the electric vehicle components; Based on the modular design and the standardized interface, analyzing the electric vehicle production demand and formulating the electric vehicle assembly plan; Allocating the assembly plan to each workstation device; Selecting a neural network structure to construct an electric vehicle assembly monitoring model, monitoring the electric vehicle assembly process through the electric vehicle assembly monitoring model, and obtaining an electric vehicle assembly monitoring result; The assembly plan is adjusted according to the electric vehicle assembly monitoring result.

[0006] Furthermore, the electric vehicle components are modularly designed and standardized interfaces are developed for the electric vehicle components, including: Determine the electric vehicle components, perform modular design on the electric vehicle components, and define the functions and design requirements of each modular component; Designing standardized interfaces for the modular components based on the functions and design requirements of the modular components; Performing integration testing on the modular components and the standardized interfaces, and optimizing the modular components according to the integration testing results; The optimized modular components are numbered in a standardized manner to establish a modular component library.

[0007] Furthermore, based on the modular design and the standardized interface, the electric vehicle production demand is analyzed and the electric vehicle assembly plan is formulated, including: Collecting production demands of the electric vehicles and sorting the production demands; Matching the modular component library according to the sorted production requirements to determine the required modular components; Conduct production line resource configuration analysis, and formulate the electric vehicle assembly plan based on the required modular components and the production line resource configuration.

[0008] Furthermore, the production requirements are sorted, including: Specifying the sorting criteria of the production requirements and assigning a weight to each of the sorting criteria; Determine a scoring range, and score each of the production requirements according to the scoring range; A weighted total score of each production requirement is calculated according to the weight and the score, and the production requirements are sorted according to the weighted total score.

[0009] Furthermore, a neural network structure is selected to construct an electric vehicle assembly monitoring model, including: Collecting key data in the electric vehicle assembly process to obtain a data set; Dividing the data set into a training set, a validation set, and a test set; Designing a neural network model architecture and compiling the neural network model; Using the training set and the validation set to train the compiled neural network model, and using the test set to evaluate the trained neural network model to obtain a model evaluation result; The neural network model is adjusted and optimized according to the model evaluation result to obtain an electric vehicle assembly monitoring model.

[0010] Furthermore, the designing of the neural network model architecture and compiling the neural network model include: An input layer, for receiving key data in the electric vehicle assembly process; A recurrent layer processes sequence data and captures the temporal dependencies of the sequence data; In the fully connected layer, each neuron is connected to all neurons in the previous layer, mapping the output of the previous layer to a new space; Layer normalization, normalizing the features of each of the key data; The activation layer introduces nonlinear characteristics so that the neural network model can learn more complex functions and features; Output layer, which produces the final prediction result; Select appropriate optimizers, loss functions, and evaluation metrics for the neural network model.

[0011] Furthermore, when the compiled neural network model is trained using the training set and the validation set, a gradient clipping technique is used to limit the norm of the gradient.

[0012] Furthermore, an emergency response mechanism is provided during the electric vehicle assembly process.

[0013] An intelligent automatic assembly system for electric vehicle components, the system comprising: A modular design module for modularly designing electric vehicle components and developing standardized interfaces for the electric vehicle components; An assembly plan formulation module, which analyzes the production demand of electric vehicles and formulates the assembly plan of the electric vehicles based on the modular design and the standardized interface; An assembly plan allocation module allocates the assembly plan to each workstation device; A monitoring model building module selects a neural network structure to build an electric vehicle assembly monitoring model, monitors the electric vehicle assembly process through the electric vehicle assembly monitoring model, and obtains an electric vehicle assembly monitoring result; An assembly plan adjustment module adjusts the assembly plan according to the electric vehicle assembly monitoring result.

[0014] Furthermore, the assembly plan making module includes: A production demand collection unit, which collects the production demand of the electric vehicle and sorts the production demand; A component matching unit matches the modular component library according to the sorted production requirements to determine the required modular components; The resource configuration analysis unit performs production line resource configuration analysis and formulates the electric vehicle assembly plan based on the required modular components and the production line resource configuration.

[0015] The technical solution of the present invention can achieve the following technical effects: The present invention introduces modular design and standardized interfaces, and adopts advanced neural network technology and intelligent monitoring systems, which helps to improve the efficiency of electric vehicle assembly, and can adjust assembly strategies in a timely manner, enhance production flexibility and optimal allocation of resources, and help achieve flexible manufacturing of electric vehicles with multiple models and configurations.

[0016] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 A schematic diagram of a process for intelligent and automated assembly of electric vehicle components; Figure 2 A schematic diagram of the process for developing an electric vehicle assembly plan; Figure 3 The figure is a structural diagram of an intelligent and automated assembly system for electric vehicle components. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0021] Embodiment 1 like Figure 1 As shown, an intelligent automatic assembly method for electric vehicle components, the method comprising: A1: Modularize the design of electric vehicle components and develop standardized interfaces for electric vehicle components; Specifically, modular design can divide electric vehicle components into several standardized independent component modules, such as battery systems, power systems, frames, etc., and each module can be produced and tested separately; in order to facilitate the interchange and combination of different modules, standardized interfaces can be designed for each module to ensure that these modules can be seamlessly connected and collaborated, making the assembly process more flexible and efficient.

[0022] A2: Analyze electric vehicle production needs and develop electric vehicle assembly plans based on modular design and standardized interfaces; A3: Allocate the assembly plan to each workstation equipment; Based on the existing modular design and standardized interfaces, we can analyze market demand and production orders, and formulate detailed assembly plans, including the assembly sequence, time schedule, resource allocation, etc. of each module, to ensure that the production tasks can be completed efficiently; the formulated assembly plan will be assigned to each workstation and automated equipment to ensure that each module is assembled at the correct time, place and conditions, and the assembly of the entire electric vehicle can be completed through the collaborative work of automated equipment.

[0023] A4: Select a neural network structure to build an electric vehicle assembly monitoring model, monitor the electric vehicle assembly process through the electric vehicle assembly monitoring model, and obtain the electric vehicle assembly monitoring results; A5: Adjust the assembly plan based on the electric vehicle assembly monitoring results.

[0024] This step uses a neural network model to monitor the assembly process of electric vehicles. Appropriate neural network structures can be selected, including convolutional neural networks, recurrent neural networks, and fully connected neural networks. To ensure its effectiveness in practical applications, the model can be trained and evaluated, and the trained model can be deployed in a production environment. It can be run as part of a real-time monitoring system to monitor the assembly process in real time and adjust the assembly plan based on the monitoring results.

[0025] This solution forms a closed-loop feedback mechanism by combining planning and model monitoring. First, a plan is made, then it is executed, monitored in real time, and optimized and adjusted according to the monitoring results, ultimately forming a production process that continuously improves itself. Before starting assembly, there must be a basic assembly plan to guide the operation of each workstation and equipment. By allocating the assembly plan first, the entire assembly process can be carried out according to the predetermined steps and schedule, which helps to maintain the continuity and efficiency of production. Various uncertainties may be encountered during the assembly process, such as equipment failures, material delays, etc. The monitoring model based on the neural network can collect data in real time and monitor the assembly process. If deviations or potential problems are detected in the assembly process, the model can make adjustment suggestions to ensure the final product quality and production efficiency.

[0026] The present invention introduces modular design and standardized interfaces, and adopts advanced neural network technology and intelligent monitoring systems, which helps to improve the efficiency of electric vehicle assembly, and can adjust assembly strategies in a timely manner, enhance production flexibility and optimal allocation of resources, and help achieve flexible manufacturing of electric vehicles with multiple models and configurations.

[0027] Based on the above embodiments, the electric vehicle components are modularly designed, and standardized interfaces are developed for the electric vehicle components, including: B1: Identify electric vehicle components, conduct modular design of electric vehicle components, and define the functions and design requirements of each modular component; The principle of modular design in this step is to decompose the entire electric vehicle into relatively independent modules, such as battery module, control module, drive module, frame module, etc. Each module should have specific functions. Modular design helps to improve the flexible manufacturing capabilities of the production line, so that electric vehicles of different models or configurations can be assembled on the same production line. Define the specific functional scope and design requirements for each module. The versatility and scalability of the module should be considered during design to adapt to possible future updates or upgrades. Through reasonable functional division, it can be ensured that each module can be independent of each other and seamlessly connected during assembly.

[0028] B2: Design standardized interfaces for modular components based on their functions and design requirements; Specifically, in order to ensure the compatibility and consistency of different modules in physical connection and information transmission, standardized interfaces can be designed for the modules to ensure that different modules can be connected quickly and reliably, thereby achieving the universality and interchangeability of the modules and simplifying subsequent assembly and maintenance. The design steps for standardized interfaces include: Define interface standards: Develop interface standards for connections between modules, including mechanical connection standards (such as bolt hole size, snap-on design, etc.) and electrical interface standards (such as voltage level, communication protocol, etc.).

[0029] Interface compatibility test: Test the compatibility of interfaces to ensure seamless connection between different modules and meet design requirements.

[0030] Develop interface components: According to the interface standards, develop corresponding interface components, such as connectors, plug-ins, etc., and conduct small-batch trial production and verification.

[0031] Interface documentation: Write detailed interface standard documents, including interface dimensions, materials, connection methods, instructions for use, etc., to provide guidance for subsequent manufacturing and assembly.

[0032] B3: Conduct integration testing on modular components and standardized interfaces, and optimize modular components based on the integration testing results; In this embodiment, in order to verify whether the module design and interface meet the actual needs, the modules can be assembled according to the design requirements, the matching degree between the modules and the reliability of the interface connection can be verified, and the assembled modules can be functionally tested to ensure that they can work normally after integration and meet the design specifications. If problems are found during the integration test, fault analysis can be performed to find the root cause of the problem and make adjustments and optimizations to ensure the feasibility and stability of the module design.

[0033] B4: Standardize the numbering of optimized modular components and establish a modular component library.

[0034] In this step, the developed modular components can be numbered in a standardized manner and a modular component library can be established for subsequent production and maintenance. The component library should contain the design drawings, interface instructions, assembly guides, etc. of each module. The establishment of a modular component library helps to improve production efficiency, especially in customized production, as standardized modules can be quickly called for combination, greatly shortening the design and production cycle.

[0035] As the preferred embodiment of this invention, Figure 2 As shown in the figure, based on modular design and standardized interfaces, electric vehicle production needs are analyzed and electric vehicle assembly plans are formulated, including: C1: Collect production demand for electric vehicles and sort the production demand; Specifically, in order to clarify production goals and priorities and ensure that assembly plans can meet market demand and production capacity, production needs can be collected and sorted. Data from market analysis, customer orders and internal sales forecasts can be collected through customer order management systems, market research and other channels, covering demand information such as electric vehicle models, configurations, production quantities and delivery times; the collected production demand data can be classified, and different orders can be sorted through priority sorting, bottleneck analysis, critical path method and other methods, giving priority to urgent orders or large-scale production needs; adding a step of data cleaning and verification after data collection to remove redundant data and supplement missing data can ensure that the basis for classification and sorting is reliable.

[0036] C2: Match the modular component library according to the sorted production requirements and determine the required modular components; C3: Conduct production line resource allocation analysis and formulate an electric vehicle assembly plan based on the required modular components and production line resource allocation.

[0037] This step analyzes the resource allocation of the production line and evaluates factors such as the production capacity, equipment utilization, and worker allocation of each production line to determine the optimal resource allocation plan. By comprehensively considering the matching modular components and production line resources, a detailed assembly plan can be developed to clarify the assembly tasks, time schedules, and workstation allocations for each production batch.

[0038] Based on the above embodiment, the production requirements are sorted, including: D1: Clarify the sorting criteria for production needs and assign weights to each sorting criterion; D2: Determine the scoring range and score each production requirement according to the scoring range; D3: Calculate the weighted total score of each production requirement based on the weight and score, and sort the production requirements by the weighted total score.

[0039] Specifically, delivery time, cost benefit, etc. can be selected as sorting criteria, and the setting of sorting criterion weights should fully consider the relationship between the criteria to avoid distortion of the sorting results due to excessive weight of a certain criterion. The weights can be set through expert opinions, historical data analysis or market research; when scoring, in order to ensure the fairness and consistency of the scoring process, consistency checks can be performed to avoid human bias. The total score of the sorting criteria can be calculated through weights and scores for unified sorting. The calculation formula is as follows: Weighted total score = ∑(standard score × standard weight).

[0040] As a preferred embodiment of this invention, a neural network structure is selected to construct an electric vehicle assembly monitoring model, including: E1: Collect key data in the electric vehicle assembly process and obtain a data set; The key data collected in the electric vehicle assembly process in this embodiment may include assembly time, component availability, assembly accuracy, equipment status, etc., to construct a data set containing various assembly parameters, status and results, to provide a basis for the training of the neural network model, to ensure that the data volume is sufficient and covers all key links, and the data should be diverse and representative. In order to make the data more suitable for the training of the neural network model and reduce the redundancy and complexity of the data, the collected data can be preprocessed, cleaned, missing values ​​and outliers can be processed, and the data can be standardized or normalized to ensure that different features are learned on the same scale.

[0041] E2: Divide the dataset into training set, validation set and test set; E3: Design the neural network model architecture and compile the neural network model; E4: Use the training set and validation set to train the compiled neural network model, and use the test set to evaluate the trained neural network model to obtain the model evaluation results; Specifically, the model is trained, evaluated and optimized through training sets, validation sets and test sets. The model is trained multiple times using the data in the training set. The training set usually contains a large number of samples, each of which includes input data and corresponding labels. Through repeated iterations, the weights and biases of the neural network model are adjusted so that the model can learn the mapping relationship between input and output from the training data. During the training process, the validation set is specifically used to monitor the performance of the model on unseen data to determine whether the model is overfitting or underfitting. The validation set is used to evaluate the performance of the model, prevent overfitting, and make hyperparameter adjustments. The test set is data that is not used at all in the training process. By calculating the performance indicators of the model on the test set, such as accuracy, F1 score, ROC-AUC curve, etc., the final trained model is independently evaluated to verify the actual performance of the model.

[0042] E5: According to the model evaluation results, the neural network model is adjusted and optimized to obtain the electric vehicle assembly monitoring model.

[0043] On the basis of the above embodiment, a neural network model architecture is designed and the neural network model is compiled, including: The input layer is used to receive key data in the electric vehicle assembly process; it defines the input shape of the data to ensure that subsequent layers can correctly process the input data.

[0044] The recurrent layer processes sequence data and captures the temporal dependencies of sequence data. It can learn long-term dependencies and temporal patterns in sequences through memory and update mechanisms.

[0045] In the fully connected layer, each neuron is connected to all neurons in the previous layer, mapping the output of the previous layer to a new space; Layer normalization normalizes the features of each key data; layer normalization normalizes each feature, which can help speed up the training process and improve the stability of the model. Layer normalization can increase the convergence speed of the network and alleviate the problem of gradient explosion or disappearance by standardizing the output of each layer and reducing internal covariate shift.

[0046] The activation layer introduces nonlinear characteristics, allowing the neural network model to learn more complex functions and features. In the fully connected layer of the neural network, the output of each layer is a linear combination of the output of the previous layer, and the combination of multiple linear layers is still a linear relationship, which limits the network's expressive power. The activation layer breaks this linear relationship by applying nonlinear functions such as ReLU, Sigmoid, Tanh, etc., allowing the neural network to solve complex nonlinear problems and enhance the neural network's expressive power.

[0047] Output layer, which produces the final prediction result; Choose appropriate optimizers, loss functions, and evaluation metrics for your neural network models.

[0048] After compiling the designed neural network model, you can select the appropriate optimizer, loss function and evaluation index to effectively train the model. The optimizer is used to update the model weights to minimize the loss function. Common optimizers include Adam and SGD. The loss function is used to calculate the error between the model prediction and the actual result. Selecting the appropriate loss function is an important part of model training. The cross entropy loss function is commonly used in classification tasks, and the mean square error is commonly used in regression tasks. Evaluation indicators are used to evaluate the performance of the model, including accuracy, precision, recall, etc.

[0049] In order to make the training process of the neural network model smoother, the gradient clipping technology is used to limit the norm of the gradient when training the compiled neural network model using the training set and the validation set.

[0050] Gradient clipping is a technique commonly used to prevent the gradient explosion problem when training deep neural networks, especially recurrent neural networks. In deep neural networks, especially recurrent neural networks, due to multiple backpropagations, the gradient value may become very large in some cases, resulting in excessive updates of model parameters, and ultimately causing the model to fail to converge or perform poorly. Gradient clipping can prevent the gradient value from being too large by limiting the norm of the gradient to a predetermined threshold range, thereby avoiding the model from being unable to train normally, making the training process smoother and helping the model converge better.

[0051] Furthermore, an emergency response mechanism is set up during the electric vehicle assembly process.

[0052] When major unpredictable emergencies occur, such as equipment failures or large-scale order changes, the fault emergency response mechanism can be activated to quickly adjust the assembly plan, or temporarily suspend production to troubleshoot or re-evaluate the production strategy. The emergency response mechanism is a supplement to the dynamic adjustment mechanism, ensuring that the production process can still operate stably and reduce losses in the most extreme cases. The emergency response mechanism uses sensors and monitoring systems to capture possible abnormal situations in the production process in real time and issue early warning signals in advance. When a parameter exceeds the preset threshold, the system will automatically trigger an emergency response and automatically execute the predetermined emergency handling procedures after detecting the problem; when the automated system cannot solve the problem, the system provides the necessary information and tools to support manual intervention and decision-making.

[0053] Embodiment 2 like Figure 3 As shown, an intelligent automatic assembly system for electric vehicle components, the system includes: Modular design module, which conducts modular design of electric vehicle components and develops standardized interfaces for electric vehicle components; The assembly plan making module analyzes the production demand of electric vehicles and makes an assembly plan for electric vehicles based on modular design and standardized interfaces; Assembly plan allocation module allocates assembly plans to each workstation equipment; The monitoring model building module selects a neural network structure to build an electric vehicle assembly monitoring model, monitors the electric vehicle assembly process through the electric vehicle assembly monitoring model, and obtains the electric vehicle assembly monitoring results; The assembly plan adjustment module adjusts the assembly plan according to the electric vehicle assembly monitoring results.

[0054] The above-mentioned adjustment system in the present invention can effectively realize the intelligent and automated assembly method of electric vehicle components, and the technical effects that can be achieved are as described in the above-mentioned embodiments, which will not be repeated here.

[0055] Furthermore, the assembly planning module includes: A production demand collection unit collects production demands of electric vehicles and sorts the production demands; The component matching unit matches the modular component library according to the sorted production requirements and determines the required modular components; The resource allocation analysis unit conducts production line resource allocation analysis and formulates an electric vehicle assembly plan based on the required modular components and production line resource allocation.

[0056] Similarly, the above-mentioned optimization schemes for the system can also respectively achieve the optimization effects corresponding to the method in Example 1, which will not be repeated here.

[0057] Although the present application has been described in conjunction with specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the accompanying drawings are merely exemplary illustrations of the present application as defined herein, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application is intended to include these modifications and variations.

Claims

1. An intelligent and automated assembly method for electric vehicle components, characterized in that: The method comprises: Modularize the design of electric vehicle components and develop standardized interfaces for the electric vehicle components; Based on the modular design and the standardized interface, analyzing the electric vehicle production demand and formulating the electric vehicle assembly plan; Allocating the assembly plan to each workstation device; Selecting a neural network structure to construct an electric vehicle assembly monitoring model, monitoring the electric vehicle assembly process through the electric vehicle assembly monitoring model, and obtaining an electric vehicle assembly monitoring result; The assembly plan is adjusted according to the electric vehicle assembly monitoring result.

2. The intelligent automatic assembly method of electric vehicle components according to claim 1, characterized in that: Modular design of electric vehicle components and development of standardized interfaces for the electric vehicle components, including: Determine the electric vehicle components, perform modular design on the electric vehicle components, and define the functions and design requirements of each modular component; Designing standardized interfaces for the modular components based on the functions and design requirements of the modular components; Performing integration testing on the modular components and the standardized interfaces, and optimizing the modular components according to the integration testing results; The optimized modular components are numbered in a standardized manner to establish a modular component library.

3. The intelligent and automated assembly method for electric vehicle components according to claim 1, characterized in that: Based on the modular design and the standardized interface, the electric vehicle production demand is analyzed and the electric vehicle assembly plan is formulated, including: Collecting production demands of the electric vehicles and sorting the production demands; Matching the modular component library according to the sorted production requirements to determine the required modular components; Conduct production line resource configuration analysis, and formulate the electric vehicle assembly plan based on the required modular components and the production line resource configuration.

4. The intelligent automatic assembly method of electric vehicle components according to claim 3, characterized in that: Prioritize the production requirements, including: Specifying the sorting criteria of the production requirements and assigning a weight to each of the sorting criteria; Determine a scoring range, and score each of the production requirements according to the scoring range; A weighted total score of each production requirement is calculated according to the weight and the score, and the production requirements are sorted according to the weighted total score.

5. The intelligent and automated assembly method for electric vehicle components according to claim 1, characterized in that: Select the neural network structure to build an electric vehicle assembly monitoring model, including: Collecting key data in the electric vehicle assembly process to obtain a data set; Dividing the data set into a training set, a validation set, and a test set; Designing a neural network model architecture and compiling the neural network model; Using the training set and the validation set to train the compiled neural network model, and using the test set to evaluate the trained neural network model to obtain a model evaluation result; The neural network model is adjusted and optimized according to the model evaluation result to obtain an electric vehicle assembly monitoring model.

6. The intelligent automatic assembly method of electric vehicle components according to claim 5, characterized in that: The designing of the neural network model architecture and compiling the neural network model include: An input layer, for receiving key data in the electric vehicle assembly process; A recurrent layer processes sequence data and captures the temporal dependencies of the sequence data; In the fully connected layer, each neuron is connected to all neurons in the previous layer, mapping the output of the previous layer to a new space; Layer normalization, normalizing the features of each of the key data; The activation layer introduces nonlinear characteristics so that the neural network model can learn more complex functions and features; Output layer, which produces the final prediction result; Select appropriate optimizers, loss functions, and evaluation metrics for the neural network model.

7. The intelligent automatic assembly method of electric vehicle components according to claim 5, characterized in that: When the compiled neural network model is trained using the training set and the validation set, a gradient clipping technique is used to limit the norm of the gradient.

8. The intelligent and automated assembly method for electric vehicle components according to claim 1, characterized in that: An emergency response mechanism is provided during the electric vehicle assembly process.

9. An intelligent and automated assembly system for electric vehicle components, characterized in that: The system comprises: A modular design module for modularly designing electric vehicle components and developing standardized interfaces for the electric vehicle components; An assembly plan formulation module, which analyzes the production demand of electric vehicles and formulates the assembly plan of the electric vehicles based on the modular design and the standardized interface; An assembly plan allocation module allocates the assembly plan to each workstation device; A monitoring model building module selects a neural network structure to build an electric vehicle assembly monitoring model, monitors the electric vehicle assembly process through the electric vehicle assembly monitoring model, and obtains an electric vehicle assembly monitoring result; An assembly plan adjustment module adjusts the assembly plan according to the electric vehicle assembly monitoring result.

10. The intelligent automatic assembly system for electric vehicle components according to claim 9, characterized in that: The assembly plan making module includes: A production demand collection unit, which collects the production demand of the electric vehicle and sorts the production demand; A component matching unit matches the modular component library according to the sorted production requirements to determine the required modular components; The resource configuration analysis unit performs production line resource configuration analysis and formulates the electric vehicle assembly plan based on the required modular components and the production line resource configuration.

Images